The Aggregate - Lichess Rating Prediction (10-game Pilot): leaderboard

Predict each player’s pre-game Lichess rapid Glicko-2 rating from an anonymized standard 10+0 game. Ten games involve twenty distinct established players, each with at least 1,000 rapid games and rating deviation at most 60 at collection. Every model sees the same frozen moves, result and time control, with no identities, ratings, engine analysis or tools. Medium reasoning is requested with an 8,192-token output cap. The score is mean absolute error across twenty player estimates, in rating points; lower is better. Only complete ten-game panels are ranked. This small sample spans five mean-rating bands and is not representative of the Lichess population. Reference predictors are not AI observations.

Source: theaggregate.ai.

Interactive version: theaggregate.ai/benchmark?slug=the-aggregate-lichess-rating-prediction-10-game-pilot · How It Works · Data refreshed daily, snapshot 2026-10-11.